Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1768 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.1725. Min Range: -1.1725

Max Act: 1.1725. Min Act: -0.0002

Data Index: 962525 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 1.1725. Min Range: -1.1725

Max Act: 1.1593. Min Act: -0.0002

Data Index: 264741 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 1.1725. Min Range: -1.1725

Max Act: 1.1130. Min Act: -0.0002

Data Index: 882172 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 1.1725. Min Range: -1.1725

Max Act: 1.1151. Min Act: -0.0002

Data Index: 789072 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 1.1725. Min Range: -1.1725

Max Act: 1.0986. Min Act: -0.0002

Data Index: 973486 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 1.1725. Min Range: -1.1725

Max Act: 1.0646. Min Act: -0.0002

Data Index: 904196 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 1.1725. Min Range: -1.1725

Max Act: 1.0848. Min Act: -0.0002

Data Index: 1214826 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 1.1725. Min Range: -1.1725

Max Act: 1.0797. Min Act: -0.0003

Data Index: 369247 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 1.1725. Min Range: -1.1725

Max Act: 1.0519. Min Act: -0.0002

Data Index: 129901 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 1.1725. Min Range: -1.1725

Max Act: 1.0459. Min Act: -0.0002

Data Index: 721678 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 1.1725. Min Range: -1.1725

Max Act: 1.0421. Min Act: -0.0002

Data Index: 320140 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 1.1725. Min Range: -1.1725

Max Act: 1.0139. Min Act: -0.0002

Data Index: 1027135 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 1.1725. Min Range: -1.1725

Max Act: 1.0187. Min Act: -0.0002

Data Index: 1112945 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.9872. Min Act: -0.0002

Data Index: 159130 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 1.1725. Min Range: -1.1725

Max Act: 1.0151. Min Act: -0.0003

Data Index: 1089470 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.9740. Min Act: -0.0002

Data Index: 782434 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.9513. Min Act: -0.0003

Data Index: 691515 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.9699. Min Act: -0.0002

Data Index: 206798 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.9473. Min Act: -0.0002

Data Index: 905166 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.9626. Min Act: -0.0002

Data Index: 743609 (C4 (Web Text))

Max Activating Token Index: 255